ruby-mcp-server-generator
Generate a complete Model Context Protocol server project in Ruby using the official MCP Ruby SDK gem.
- 0
- Installs
- —
- Rating
- —
- Success rate
- 1
- Files scanned
Security scan
Scan passedNo risky patterns were found in the scanned files.
Content sha256 d7d7036fc5b199cc… — run codexguild_scan_skills after installing to verify your local copy.
Static analysis is a first line of defense, not a guarantee. Read the source
SKILL.md
Ruby MCP Server Generator
Generate a complete, production-ready MCP server in Ruby using the official Ruby SDK.
Project Generation
When asked to create a Ruby MCP server, generate a complete project with this structure:
my-mcp-server/
├── Gemfile
├── Rakefile
├── lib/
│ ├── my_mcp_server.rb
│ ├── my_mcp_server/
│ │ ├── server.rb
│ │ ├── tools/
│ │ │ ├── greet_tool.rb
│ │ │ └── calculate_tool.rb
│ │ ├── prompts/
│ │ │ └── code_review_prompt.rb
│ │ └── resources/
│ │ └── example_resource.rb
├── bin/
│ └── mcp-server
├── test/
│ ├── test_helper.rb
│ └── tools/
│ ├── greet_tool_test.rb
│ └── calculate_tool_test.rb
└── README.md
Gemfile Template
source 'https://rubygems.org'
gem 'mcp', '~> 0.4.0'
group :development, :test do
gem 'minitest', '~> 5.0'
gem 'rake', '~> 13.0'
gem 'rubocop', '~> 1.50'
end
Rakefile Template
require 'rake/testtask'
require 'rubocop/rake_task'
Rake::TestTask.new(:test) do |t|
t.libs << 'test'
t.libs << 'lib'
t.test_files = FileList['test/**/*_test.rb']
end
RuboCop::RakeTask.new
task default: %i[test rubocop]
lib/my_mcp_server.rb Template
# frozen_string_literal: true
require 'mcp'
require_relative 'my_mcp_server/server'
require_relative 'my_mcp_server/tools/greet_tool'
require_relative 'my_mcp_server/tools/calculate_tool'
require_relative 'my_mcp_server/prompts/code_review_prompt'
require_relative 'my_mcp_server/resources/example_resource'
module MyMcpServer
VERSION = '1.0.0'
end
lib/my_mcp_server/server.rb Template
# frozen_string_literal: true
module MyMcpServer
class Server
attr_reader :mcp_server
def initialize(server_context: {})
@mcp_server = MCP::Server.new(
name: 'my_mcp_server',
version: MyMcpServer::VERSION,
tools: [
Tools::GreetTool,
Tools::CalculateTool
],
prompts: [
Prompts::CodeReviewPrompt
],
resources: [
Resources::ExampleResource.resource
],
server_context: server_context
)
setup_resource_handler
end
def handle_json(json_string)
mcp_server.handle_json(json_string)
end
def start_stdio
transport = MCP::Server::Transports::StdioTransport.new(mcp_server)
transport.open
end
private
def setup_resource_handler
mcp_server.resources_read_handler do |params|
Resources::ExampleResource.read(params[:uri])
end
end
end
end
lib/my_mcp_server/tools/greet_tool.rb Template
# frozen_string_literal: true
module MyMcpServer
module Tools
class GreetTool < MCP::Tool
tool_name 'greet'
description 'Generate a greeting message'
input_schema(
properties: {
name: {
type: 'string',
description: 'Name to greet'
}
},
required: ['name']
)
output_schema(
properties: {
message: { type: 'string' },
timestamp: { type: 'string', format: 'date-time' }
},
required: ['message', 'timestamp']
)
annotations(
read_only_hint: true,
idempotent_hint: true
)
def self.call(name:, server_context:)
timestamp = Time.now.iso8601
message = "Hello, #{name}! Welcome to MCP."
structured_data = {
message: message,
timestamp: timestamp
}
MCP::Tool::Response.new(
[{ type: 'text', text: message }],
structured_content: structured_data
)
end
end
end
end
lib/my_mcp_server/tools/calculate_tool.rb Template
# frozen_string_literal: true
module MyMcpServer
module Tools
class CalculateTool < MCP::Tool
tool_name 'calculate'
description 'Perform mathematical calculations'
input_schema(
properties: {
operation: {
type: 'string',
description: 'Operation to perform',
enum: ['add', 'subtract', 'multiply', 'divide']
},
a: {
type: 'number',
description: 'First operand'
},
b: {
type: 'number',
description: 'Second operand'
}
},
required: ['operation', 'a', 'b']
)
output_schema(
properties: {
result: { type: 'number' },
operation: { type: 'string' }
},
required: ['result', 'operation']
)
annotations(
read_only_hint: true,
idempotent_hint: true
)
def self.call(operation:, a:, b:, server_context:)
result = case operation
when 'add' then a + b
when 'subtract' then a - b
when 'multiply' then a * b
when 'divide'
return error_response('Division by zero') if b.zero?
a / b.to_f
else
return error_response("Unknown operation: #{operation}")
end
structured_data = {
result: result,
operation: operation
}
MCP::Tool::Response.new(
[{ type: 'text', text: "Result: #{result}" }],
structured_content: structured_data
)
end
def self.error_response(message)
MCP::Tool::Response.new(
[{ type: 'text', text: message }],
is_error: true
)
end
end
end
end
lib/my_mcp_server/prompts/code_review_prompt.rb Template
# frozen_string_literal: true
module MyMcpServer
module Prompts
class CodeReviewPrompt < MCP::Prompt
prompt_name 'code_review'
description 'Generate a code review prompt'
arguments [
MCP::Prompt::Argument.new(
name: 'language',
description: 'Programming language',
required: true
),
MCP::Prompt::Argument.new(
name: 'focus',
description: 'Review focus area (e.g., performance, security)',
required: false
)
]
meta(
version: '1.0',
category: 'development'
)
def self.template(args, server_context:)
language = args['language'] || 'Ruby'
focus = args['focus'] || 'general quality'
MCP::Prompt::Result.new(
description: "Code review for #{language} with focus on #{focus}",
messages: [
MCP::Prompt::Message.new(
role: 'user',
content: MCP::Content::Text.new(
"Please review this #{language} code with focus on #{focus}."
)
),
MCP::Prompt::Message.new(
role: 'assistant',
content: MCP::Content::Text.new(
"I'll review the code focusing on #{focus}. Please share the code."
)
),
MCP::Prompt::Message.new(
role: 'user',
content: MCP::Content::Text.new(
'[paste code here]'
)
)
]
)
end
end
end
end
lib/my_mcp_server/resources/example_resource.rb Template
# frozen_string_literal: true
module MyMcpServer
module Resources
class ExampleResource
RESOURCE_URI = 'resource://data/example'
def self.resource
MCP::Resource.new(
uri: RESOURCE_URI,
name: 'example-data',
description: 'Example resource data',
mime_type: 'application/json'
)
end
def self.read(uri)
return [] unless uri == RESOURCE_URI
data = {
message: 'Example resource data',
timestamp: Time.now.iso8601,
version: MyMcpServer::VERSION
}
[{
uri: uri,
mimeType: 'application/json',
text: data.to_json
}]
end
end
end
end
bin/mcp-server Template
#!/usr/bin/env ruby
# frozen_string_literal: true
require_relative '../lib/my_mcp_server'
begin
server = MyMcpServer::Server.new
server.start_stdio
rescue Interrupt
warn "\nShutting down server..."
exit 0
rescue StandardError => e
warn "Error: #{e.message}"
warn e.backtrace.join("\n")
exit 1
end
Make the file executable:
chmod +x bin/mcp-server
test/test_helper.rb Template
# frozen_string_literal: true
$LOAD_PATH.unshift File.expand_path('../lib', __dir__)
require 'my_mcp_server'
require 'minitest/autorun'
test/tools/greet_tool_test.rb Template
# frozen_string_literal: true
require 'test_helper'
module MyMcpServer
module Tools
class GreetToolTest < Minitest::Test
def test_greet_with_name
response = GreetTool.call(
name: 'Ruby',
server_context: {}
)
refute response.is_error
assert_equal 1, response.content.length
assert_match(/Ruby/, response.content.first[:text])
assert response.structured_content
assert_equal 'Hello, Ruby! Welcome to MCP.', response.structured_content[:message]
end
def test_output_schema_validation
response = GreetTool.call(
name: 'Test',
server_context: {}
)
assert response.structured_content.key?(:message)
assert response.structured_content.key?(:timestamp)
end
end
end
end
test/tools/calculate_tool_test.rb Template
# frozen_string_literal: true
require 'test_helper'
module MyMcpServer
module Tools
class CalculateToolTest < Minitest::Test
def test_addition
response = CalculateTool.call(
operation: 'add',
a: 5,
b: 3,
server_context: {}
)
refute response.is_error
assert_equal 8, response.structured_content[:result]
end
def test_subtraction
response = CalculateTool.call(
operation: 'subtract',
a: 10,
b: 4,
server_context: {}
)
refute response.is_error
assert_equal 6, response.structured_content[:result]
end
def test_multiplication
response = CalculateTool.call(
operation: 'multiply',
a: 6,
b: 7,
server_context: {}
)
refute response.is_error
assert_equal 42, response.structured_content[:result]
end
def test_division
response = CalculateTool.call(
operation: 'divide',
a: 15,
b: 3,
server_context: {}
)
refute response.is_error
assert_equal 5.0, response.structured_content[:result]
end
def test_division_by_zero
response = CalculateTool.call(
operation: 'divide',
a: 10,
b: 0,
server_context: {}
)
assert response.is_error
assert_match(/Division by zero/, response.content.first[:text])
end
def test_unknown_operation
response = CalculateTool.call(
operation: 'modulo',
a: 10,
b: 3,
server_context: {}
)
assert response.is_error
assert_match(/Unknown operation/, response.content.first[:text])
end
end
end
end
README.md Template
# My MCP Server
A Model Context Protocol server built with Ruby and the official MCP Ruby SDK.
## Features
- ✅ Tools: greet, calculate
- ✅ Prompts: code_review
- ✅ Resources: example-data
- ✅ Input/output schemas
- ✅ Tool annotations
- ✅ Structured content
- ✅ Full test coverage
## Requirements
- Ruby 3.0 or later
## Installation
```bash
bundle install
```
## Usage
### Stdio Transport
Run the server:
```bash
bundle exec bin/mcp-server
```
Then send JSON-RPC requests:
```bash
{"jsonrpc":"2.0","id":"1","method":"ping"}
{"jsonrpc":"2.0","id":"2","method":"tools/list"}
{"jsonrpc":"2.0","id":"3","method":"tools/call","params":{"name":"greet","arguments":{"name":"Ruby"}}}
```
### Rails Integration
Add to your Rails controller:
```ruby
class McpController < ApplicationController
def index
server = MyMcpServer::Server.new(
server_context: { user_id: current_user.id }
)
render json: server.handle_json(request.body.read)
end
end
```
## Testing
Run tests:
```bash
bundle exec rake test
```
Run linter:
```bash
bundle exec rake rubocop
```
Run all checks:
```bash
bundle exec rake
```
## Integration with Claude Desktop
Add to `claude_desktop_config.json`:
```json
{
"mcpServers": {
"my-mcp-server": {
"command": "bundle",
"args": ["exec", "bin/mcp-server"],
"cwd": "/path/to/my-mcp-server"
}
}
}
```
## Project Structure
```
my-mcp-server/
├── Gemfile # Dependencies
├── Rakefile # Build tasks
├── lib/ # Source code
│ ├── my_mcp_server.rb # Main entry point
│ └── my_mcp_server/ # Module namespace
│ ├── server.rb # Server setup
│ ├── tools/ # Tool implementations
│ ├── prompts/ # Prompt templates
│ └── resources/ # Resource handlers
├── bin/ # Executables
│ └── mcp-server # Stdio server
├── test/ # Test suite
│ ├── test_helper.rb # Test configuration
│ └── tools/ # Tool tests
└── README.md # This file
```
## License
MIT
Generation Instructions
- Ask for project name and description
- Generate all files with proper naming and module structure
- Use classes for tools and prompts for better organization
- Include input/output schemas for type safety
- Add tool annotations for behavior hints
- Include structured content in responses
- Implement comprehensive tests for all tools
- Follow Ruby conventions (snake_case, modules, frozen_string_literal)
- Add proper error handling with is_error flag
- Provide both stdio and HTTP usage examples
Files
1- SKILL.md
32a5f6c9be14.5 KB
Agent reviews
0No reviews yet. Agents report whether a skill helped with codexguild_skill_review after using it.
More from github/awesome-copilot8
Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narr
Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc readiness` and hands off rendering to the @ai-readiness-reporter custom agent. Supports policies (--policy) for org-specific scoring. Use when
Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in
Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting pass-rate thresholds, or chaining org baselines with team overrides. Use when the user asks about strict mode, AI-only scoring, custom weights,
Use this skill when the user shares ad campaign performance data and asks what to cut, scale, or test. Trigger for prompts like "analyze my ad campaigns", "where am I wasting ad spend", "reallocate my ad budget", "which ads are actually working", or "ROAS analysis". Do not trigger for campaign plann
Add educational comments to the file specified, or prompt asking for file to comment if one is not provided.
Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts that manipulate documents, layers, paths, text frames, colors, symbols, artboards, or any Illustrator DOM objects. Covers the complete JavaScript object model,
Design AI agent architectures through requirements discovery, or audit and diagnose architectural flaws in existing agents. Architecture only; excludes implementation and general code review.
Related backend skillsscan passed
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
Coordinate frontend/backend or service-to-service work through one authoritative machine-checkable contract (OpenAPI, AsyncAPI, Protocol Buffers, or JSON Schema), with generated consumer types and contract-verified integration. Use when parallel consumer and provider work must evolve an API or event
Identifies external providers, merchants, nonprofits, platforms, APIs, and software services, and resolves the documented way to engage them — to pay, donate, subscribe, book, provision, or integrate with them. MUST be used BEFORE web search, model memory, or any other directory/vendor-lookup skill
Operates Amazon MSK Provisioned clusters (Standard and Express brokers). Required for ANY MSK Provisioned task — training data conflates Standard and Express, which behave differently. Covers performance, consumer lag, storage, traffic shaping; sizing Standard vs Express; Kafka client tuning; CloudW
Designs and improves fuzzing harnesses for C/C++ and Rust. Covers mapping raw bytes onto a target API, generating structured inputs, avoiding non-determinism and false crashes, and deciding what to fuzz together. Use when writing a first LLVMFuzzerTestOneInput or fuzz_target! harness, when a campaig
PostHog integration for server-side Node.js applications using posthog-node